NVIDIA GeForce GTX 750 vs NVIDIA GeForce GTX 980 Comparison

Where Each One Wins

The benchmark data splits these two NVIDIA cards into entirely different performance tiers. The GTX 980 wins every recorded head-to-head test, and it does so by massive margins. The GTX 750 has no wins in the shared benchmark suite, which makes the use-case split very clear: the GTX 980 is for demanding workloads, while the GTX 750 is for basic computing tasks.

Looking at the broader database results, the GTX 980 shows its strength across multiple API types. It scores 15,163 in Geekbench Metal, 34,676 in Geekbench OpenCL, and 22,543 in Geekbench Vulkan. The GTX 750, by contrast, manages 4,274 in Metal, 9,315 in OpenCL, and 8,078 in Vulkan. Those are the only three benchmarks both cards share, and the GTX 980 wins each one with deltas of 254.8%, 272.3%, and 179.1% respectively.

The GTX 980 also has a much larger benchmark footprint in the database. It has recorded scores in 3DMark Steel Nomad DX12, PassMark DirectX 9, 10, 11, and 12, PassMark G2D, PassMark G3D, and PassMark GPU Compute. The GTX 750 only appears in the three Geekbench tests. This means the GTX 980 can be evaluated across a wider range of workloads, while the GTX 750's data is limited to compute-style benchmarks.

For use-case planning, the GTX 980 fits scenarios requiring high compute throughput, modern API support, and multi-API flexibility. The GTX 750 is suited to lighter tasks where its much lower power draw and single-slot design are advantages, but its performance envelope is clearly below the GTX 980 in every measurable way.

Architecture Differences

Both cards use TSMC's 28 nm process node, but they are built on different Maxwell generations with very different silicon. The GTX 980 uses the GM204 chip with Maxwell 2.0 architecture, while the GTX 750 uses the GM107 chip with the original Maxwell architecture. This is a fundamental generational split within NVIDIA's own lineup.

The die sizes tell the story of their performance gap. The GTX 980 packs 5,200 million transistors into a 398 mm² die, giving a transistor density of 13.1M per mm². The GTX 750 has 1,870 million transistors on a 148 mm² die, with a density of 12.6M per mm². The GTX 980 has nearly three times the transistor count and a die more than two and a half times larger.

Core resources differ enormously. The GTX 980 has 2,048 shading units, 128 texture mapping units, and 64 ROPs. The GTX 750 has 512 shading units, 32 TMUs, and 16 ROPs. That is a 4x advantage in shading units and TMUs, and a 4x advantage in ROPs for the GTX 980. The pixel rate is 77.82 GPixel/s versus 17.36 GPixel/s, and the texture rate is 155.6 GTexel/s versus 34.72 GTexel/s. The GTX 980's FP32 throughput is 4.981 TFLOPS, while the GTX 750 is rated at 1,111.0 GFLOPS.

Memory architecture also differs substantially. The GTX 980 has 4 GB of GDDR5 on a 256 bit bus, yielding 224.4 GB/s of bandwidth. The GTX 750 has 1 GB of GDDR5 on a 128 bit bus, yielding 80.19 GB/s. Memory clocks are 1753 MHz (7 Gbps effective) for the GTX 980 versus 1253 MHz (5 Gbps effective) for the GTX 750. The GTX 980's bandwidth advantage is roughly 2.8x.

Clock speeds are closer than the other specs. The GTX 980 runs at 1127 MHz base and 1216 MHz boost. The GTX 750 runs at 1020 MHz base and 1085 MHz boost. The GTX 980 is about 10% higher on both clocks, but the real gap comes from the massive core and memory differences.

Power and physical design diverge sharply. The GTX 980 has a TDP of 165 W, requires two 6-pin power connectors, and is a dual-slot card. The GTX 750 has a TDP of 55 W, requires no power connectors, and is a single-slot card. The GTX 980 is 267 mm long, while the GTX 750 is 145 mm long. Suggested PSU is 450 W for the GTX 980 versus 250 W for the GTX 750.

API support also separates them. The GTX 980 supports DirectX 12 (12_1), while the GTX 750 supports DirectX 12 (11_0). Both support OpenGL 4.6 and Vulkan 1.4. Display outputs differ: the GTX 980 has 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2, while the GTX 750 has 2x DVI and 1x mini-HDMI 1.4a.

Head-to-Head Benchmarks

The three shared benchmarks all come from the Geekbench suite, and the GTX 980 dominates each one. The largest margin is in Geekbench OpenCL, where the GTX 980 scores 34,676 against the GTX 750's 9,315. That is a delta of 272.3%, meaning the GTX 980 is nearly four times faster in this compute workload. This result aligns with the FP32 throughput difference, as OpenCL heavily exercises raw compute resources.

In Geekbench Metal, the GTX 980 scores 15,163 versus 4,274 for the GTX 750, a delta of 254.8%. Metal performance depends on both compute and graphics throughput, and the GTX 980's 4x shading unit advantage and 2.8x memory bandwidth advantage drive this result. The GTX 980 is roughly 3.5 times faster in this test.

The smallest head-to-head margin is in Geekbench Vulkan, where the GTX 980 scores 22,543 against 8,078, a delta of 179.1%. Even here, the GTX 980 is more than 2.7 times faster. Vulkan is a lower-level API that can sometimes narrow gaps between architectures, but the raw resource disparity between these two cards is too large to overcome.

Beyond the head-to-head tests, the GTX 980's standalone benchmarks provide context. Its PassMark G3D score is 11,095, and its PassMark G2D score is 792. It scores 164 in PassMark DirectX 9, 83 in DirectX 11, 53 in DirectX 10, and 46 in DirectX 12. The PassMark GPU Compute score is 4,753. The 3DMark Steel Nomad DX12 score is 474. The GTX 750 has no equivalent data in the database, so cross-card comparison for these tests is not possible.

The average benchmark score reinforces the hierarchy. The GTX 980 has an average score of 8,167 across all its recorded benchmarks, while the GTX 750 has an average of 7,222. The GTX 980 sits at the 43rd percentile among all GPUs, and the GTX 750 sits at the 40th percentile. The percentile difference is modest, but the average score gap reflects the GTX 980's broader benchmark coverage and higher absolute scores.

The Verdict

The data is unambiguous. The GTX 980 wins every shared benchmark by a minimum of 179.1% and a maximum of 272.3%. Anyone choosing between these two cards for compute-heavy or modern API workloads should select the GTX 980 without hesitation. Its 4x shading unit count, 4x ROP count, 2.8x memory bandwidth, and 4.5x FP32 throughput make it the superior choice for any task that stresses the GPU.

The GTX 750 does have its own niche. Its 55 W TDP, single-slot design, no power connectors, and 145 mm length make it suitable for compact or low-power systems where the GTX 980's 165 W TDP, dual-slot footprint, and 267 mm length would not fit. The suggested PSU of 250 W versus 450 W also matters for older or budget power supplies. For basic graphics output, legacy DirectX 9 workloads, or systems with severe space and power constraints, the GTX 750 is a viable option.

However, the performance gap is so large that the GTX 750 cannot be recommended for any modern gaming or compute workload where the GTX 980 is an option. The GTX 980's DirectX 12 (12_1) support also gives it a feature advantage over the GTX 750's DirectX 12 (11_0) support. The GTX 980's 4 GB memory capacity is four times the GTX 750's 1 GB, which matters for texture-heavy applications and larger datasets.

The nearest rivals in the database put both cards in context. The GTX 980 sits within 0.4% to 1.1% of the GTX 950M, Radeon R9 M360, GeForce 945M, and GRID K2 based on average scores. The GTX 750 sits within 0.3% to 0.9% of the Radeon Vega 8 Mobile, GTX 560 SE, Intel Iris Pro Graphics P580, and GTX 970. These rival clusters show that the GTX 980 and GTX 750 occupy different performance neighborhoods, with the GTX 980's average score about 13% higher than the GTX 750's.

For users who need maximum performance and have the power and space budget, the GTX 980 is the clear pick. For users who need a minimal-footprint, low-power card for basic tasks, the GTX 750 is the sensible choice. There is no scenario in the recorded data where the GTX 750 outperforms the GTX 980.

FAQ

Q: Which card has better compute performance in OpenCL?

A: The GTX 980 scores 34,676 in Geekbench OpenCL, which is 272.3% higher than the GTX 750's 9,315. The GTX 980 is nearly four times faster in this compute workload.

Q: How much faster is the GTX 980 in Vulkan?

A: The GTX 980 scores 22,543 in Geekbench Vulkan versus 8,078 for the GTX 750, a delta of 179.1%. The GTX 980 is more than 2.7 times faster.

Q: What are the memory capacity differences?

A: The GTX 980 has 4 GB of GDDR5 memory on a 256 bit bus with 224.4 GB/s bandwidth. The GTX 750 has 1 GB of GDDR5 on a 128 bit bus with 80.19 GB/s bandwidth.

Q: Do both cards support the same DirectX version?

A: No. The GTX 980 supports DirectX 12 (12_1), while the GTX 750 supports DirectX 12 (11_0). Both support OpenGL 4.6 and Vulkan 1.4.

Q: What are the power requirements for each card?

A: The GTX 980 has a 165 W TDP, requires two 6-pin power connectors, and needs a 450 W suggested PSU. The GTX 750 has a 55 W TDP, requires no power connectors, and needs a 250 W suggested PSU.

Q: Which card has a higher average benchmark score?

A: The GTX 980 has an average benchmark score of 8,167, while the GTX 750 has an average of 7,222. The GTX 980 also ranks at the 43rd percentile among all GPUs, compared to the 40th percentile for the GTX 750.